home.social

#vulkan — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #vulkan, aggregated by home.social.

  1. Cross-Vendor Latency Tech Arrives for Linux Gamers

    How does the new low_latency_layer help Linux gamers? It reduces input lag for AMD and Intel users by using NVIDIA Reflex technology on May 20, 2026.

    #linuxgaming, #lowlatency, #gamingtech, #vulkan, #pcgaming

    newsletter.tf/linux-low-latenc

  2. Linux gamers can now use NVIDIA Reflex and AMD Anti-Lag 2 on any GPU. This tool makes Linux gaming 15% faster in response time compared to last month.

    #linuxgaming, #lowlatency, #gamingtech, #vulkan, #pcgaming
    newsletter.tf/linux-low-latenc

  3. Linux gamers can now use NVIDIA Reflex and AMD Anti-Lag 2 on any GPU. This tool makes Linux gaming 15% faster in response time compared to last month.

    #linuxgaming, #lowlatency, #gamingtech, #vulkan, #pcgaming
    newsletter.tf/linux-low-latenc

  4. BitNet-style ternary quantization is helping bring smaller, more bandwidth-efficient LLMs to ExecuTorch through its Vulkan backend, with portable GPU execution for edge devices where performance and memory matter.

    Explore the technical details presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  5. BitNet-style ternary quantization is helping bring smaller, more bandwidth-efficient LLMs to ExecuTorch through its Vulkan backend, with portable GPU execution for edge devices where performance and memory matter.

    Explore the technical details presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  6. BitNet-style ternary quantization is helping bring smaller, more bandwidth-efficient LLMs to ExecuTorch through its Vulkan backend, with portable GPU execution for edge devices where performance and memory matter.

    Explore the technical details presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  7. BitNet-style ternary quantization is helping bring smaller, more bandwidth-efficient LLMs to ExecuTorch through its Vulkan backend, with portable GPU execution for edge devices where performance and memory matter.

    Explore the technical details presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  8. BitNet-style ternary quantization is helping bring smaller, more bandwidth-efficient LLMs to ExecuTorch through its Vulkan backend, with portable GPU execution for edge devices where performance and memory matter.

    Explore the technical details presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  9. Using COBOL As A Shader Language
    Yep, what's in the title apparently can be done.

    COBOL stands for Common Business-Oriented Language, and is an extremely verbose language designed purposely to be understandable to managers. Everything in COBOL reads like it does, which makes it hard to work with. A fair portion of the financial world still runs on COBOL, in some ca
    setsideb.com/using-cobol-as-a-
    #niche #cobol #niche #ShaderLanguage #StupidComputerTricks #Vulkan

  10. Using COBOL As A Shader Language
    Yep, what's in the title apparently can be done.

    COBOL stands for Common Business-Oriented Language, and is an extremely verbose language designed purposely to be understandable to managers. Everything in COBOL reads like it does, which makes it hard to work with. A fair portion of the financial world still runs on COBOL, in some ca
    setsideb.com/using-cobol-as-a-
    #niche #cobol #niche #ShaderLanguage #StupidComputerTricks #Vulkan

  11. Using COBOL As A Shader Language
    Yep, what's in the title apparently can be done.

    COBOL stands for Common Business-Oriented Language, and is an extremely verbose language designed purposely to be understandable to managers. Everything in COBOL reads like it does, which makes it hard to work with. A fair portion of the financial world still runs on COBOL, in some ca
    setsideb.com/using-cobol-as-a-
    #niche #cobol #niche #ShaderLanguage #StupidComputerTricks #Vulkan

  12. Using COBOL As A Shader Language
    Yep, what's in the title apparently can be done.

    COBOL stands for Common Business-Oriented Language, and is an extremely verbose language designed purposely to be understandable to managers. Everything in COBOL reads like it does, which makes it hard to work with. A fair portion of the financial world still runs on COBOL, in some ca
    setsideb.com/using-cobol-as-a-
    #niche #cobol #niche #ShaderLanguage #StupidComputerTricks #Vulkan

  13. Using COBOL As A Shader Language
    Yep, what's in the title apparently can be done.

    COBOL stands for Common Business-Oriented Language, and is an extremely verbose language designed purposely to be understandable to managers. Everything in COBOL reads like it does, which makes it hard to work with. A fair portion of the financial world still runs on COBOL, in some ca
    setsideb.com/using-cobol-as-a-
    #niche #cobol #niche #ShaderLanguage #StupidComputerTricks #Vulkan

  14. New Vulkan sample: Rasterization Order Attachment Access

    This sample demonstrates VK_EXT_rasterization_order_attachment_access, which enables framebuffer attachment reads from one fragment to the next in rasterization order, without requiring explicit synchronization or subpass self-dependencies. Techniques like programmable blending become far more practical.

    Explore the sample: github.com/KhronosGroup/Vulkan

  15. New Vulkan sample: Rasterization Order Attachment Access

    This sample demonstrates VK_EXT_rasterization_order_attachment_access, which enables framebuffer attachment reads from one fragment to the next in rasterization order, without requiring explicit synchronization or subpass self-dependencies. Techniques like programmable blending become far more practical.

    Explore the sample: github.com/KhronosGroup/Vulkan
    #Vulkan #GPU #Programming #Graphics

  16. New Vulkan sample: Rasterization Order Attachment Access

    This sample demonstrates VK_EXT_rasterization_order_attachment_access, which enables framebuffer attachment reads from one fragment to the next in rasterization order, without requiring explicit synchronization or subpass self-dependencies. Techniques like programmable blending become far more practical.

    Explore the sample: github.com/KhronosGroup/Vulkan
    #Vulkan #GPU #Programming #Graphics